Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds genuinely new behavioral facts: the operation costs 20P per successful request and its verification scope is explicitly bounded. It does not explain side effects on the document or why readOnlyHint is false despite the 'review' framing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with purpose followed by scope caveat and cost. The trailing '[20P]' redundantly restates the 20P already given, a minor waste but no real bloat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so return values need not be described, but the description leaves unclear what '입력 오류' detection produces, what the free-form document object should contain, and what state change justifies readOnlyHint=false. Adequate to call, not complete enough to predict behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are documented in the schema, so the baseline is 3. The description adds nothing about the 'document' object's expected shape, which matters because it is a free-form nested object (additionalProperties: {}), but no compensation is strictly required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('문서의 입력 오류와 확인할 문장을 검토합니다' – reviews the document for input errors and sentences needing confirmation), which is more precise than the bare name. The caveat that it does not guarantee verification of external facts implicitly separates it from the sibling document_verify, though it never names that sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to call this versus document_verify, document_assist, or document_workflow_answer; the only boundary stated is negative ('외부 사실을 검증했다고 보장하지 않습니다'). An agent must infer the appropriate context from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.